Serverless Sorcery

In this episode, Renaldi Gondosubroto and Sandeep Kumar dive into the core concepts of Large Language Models (LLMs), Prompt Engineering, Vector Databases, Retrieval-Augmented Generation (RAG), and Agents. Using Amazon Bedrock's capabilities, they’ll demystify how to leverage AI in real-world scenarios. Highlighting Sandeep's internal application, Feedbackly, they will discuss how it collects sprin...

Are your Java cloud functions too slow? What if they could start in milliseconds instead of seconds? And use less memory to boot? This is not a dream, but by changing the way we compile our Java functions we can significantly reduce memory usage while also drastically improving startup performance. Java has never been a perfect fit for Function as a Service platforms such as AWS Lambda or Azure Fu...

In this insightful episode, join me and Matt as we explore the transformative role of WebAssembly in enhancing serverless computing and generative AI workloads. We also delve into how WebAssembly is not just boosting performance but also addressing critical aspects of sustainability and security. Discover how these technologies are reshaping the landscape of development and deployment, and gain ex...

The healthcare industry is a prominent setting where Generative AI has been seen to have created a large impact. In this episode, join me and Luca discussing how he has been using it in building Neosperience's projects, the use cases that it has had that has helped doctors and patients alike, and the techniques that are employed including with agents and Retrieval Augmented Generation (RAG). We wi...

In this episode, the spotlight goes on the power of step functions and eventually consistent architectures. Listen to me and Matt talk about how Generative AI workloads can be optimized within these architectures and learn best practices of using them alongside with other features and tools within AWS that best support this. Matt has been building web applications since the 1990s. Today his focus...

In this episode, we cast the spotlight on AWS Lambda, the event-driven, serverless computing platform that's becoming the backbone of modern application development. Listen in as me and Girish dissect how Generative AI is becoming an integral part of this landscape, enhancing the agility and scalability of Lambda functions, and some Lambda projects we have worked on utilizing Generative AI. From r...

In our very first episode, join me and Bojan Zivic as we delve deep into the pioneering intersections of Cloud Development Kit (CDK), Serverless technologies, and the groundbreaking capabilities of Generative AI (GenAI). Infrastructure-as-Code (IaC) stands as a testament to tech evolution, and with GenAI entering the picture, we're on the cusp of an IaC revolution.   Join us as we: Decode the nuan...